Automatic generation of non-uniform HMM topologies based on the MDL criterion

IEICE Transactions on Information and Systems

Volumn E87-D, Issue 8, 2004, Pages 2121-2129

  Jitsuhiro, Takatoshi ^a   Matsui, Tomoko ^a,b   Nakamura, Satoshi ^a  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

^b INSTITUTE OF STATISTICAL MATHEMATICS   (Japan)

Author keywords

Acoustic model; MDL criterion; Speech recognition; SSS algorithm; Topology training

Indexed keywords

ALGORITHMS; DATABASE SYSTEMS; DECISION MAKING; ITERATIVE METHODS; MATHEMATICAL MODELS; PARAMETER ESTIMATION; STATISTICAL METHODS; TOPOLOGY;

ACOUSTIC MODEL; MDL CRITERION; SUCCESSIVE STATE SPLITTING (SSS) ALGORITHMS; TOPOLOGY TRAINING;

SPEECH RECOGNITION;

EID: 4344627406     PISSN: 09168532     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (14)

1. S.J. Young, J.J. Odell, and P.C. Woodland, "Tree-based state tying for high accuracy acoustic modeling," Proc. ARPA Workshop on Human Language Technology, pp.307-312, 1994.
2. S. Ikeda, "Construction of phone HMM using model search method," IEICE Trans. Inf. & Syst. (Japanese Edition), vol.J78-D-II, no.1, pp.10-18, Jan. 1995.
3. K. Shinoda and T. Watanabe, "Acoustic modeling based on the MDL principle for speech recognition," Proc. EUROSPEECH'97, pp.99-102, 1997.
4. K. Shinoda and T. Watanabe, "MDL-based context-dependent sub-word modeling for speech recognition," J. Acoust. Soc. Jpn. (E), vol.21, no.2, pp.79-86, 2000.
5. S.S. Chen and R.A. Gopinath, "Model selection in acoustic modeling," Proc. EUROSPEECH'99, vol.3, pp.1087-1090, 1999.
6. W. Chou and W. Reichl, "Decision tree state tying based on penalized Bayesian information criterion," Proc. ICASSP'99, vol.I, pp.345-348, 1999.
7. J. Takami and S. Sagayama, "A successive state splitting algorithm for efficient allophone modeling," Proc. ICASSP'92, vol.1, pp.573-576, 1992.
8. M. Ostendorf and H. Singer, "HMM topology design using maximum likelihood successive state splitting," Comput. Speech Lang., vol.11, pp.17-41, 1997.
9. J. Rissanen, "A universal prior for integers and estimation by minimum description length," Annals of Statistics, vol.11, pp.416-431, 1983.
10. J. Rissanen, "Universal coding, information, prediction, and estimation," IEEE Trans. Inf. Theory, vol.IT-30, no.4, pp.629-636, 1984.
11. P.A. Chou, "Optimal partitioning for classification and regression trees," IEEE Trans. Pattern Anal. Mach. Intell., vol.13, pp.340-354, 1991.
12. T. Takezawa, T. Morimoto, and Y. Sagisaka, "Speech and language databases for speech translation research in ATR," Proc. 1st International Workshop on East-Asian Language Resources and Evaluation (EALREW98), pp. 148-155, 1998.
13. H. Yamamoto and Y. Sagisaka, "Multi-class composite N-gram based on connection direction," Proc. ICASSP'99, vol.1, pp.533-536, 1999.
14. S. Furui, K. Maekawa, H. Isahara, T. Shinozaki, and T. Ohdaira, "Toward the realization of spontaneous speech recognition - Introduction of a Japanese priority program and preliminary results," Proc. ICSLP2000, vol.3, pp.518-521, 2000.